رفع النموذج النهائي مع جميع الملفات للتجربة أو إعادة التدريب

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.56.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.56.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683783f0863c43a8bf19f84b6e09a01643b2eeeed662acdc3386cec2d6182e7a
+size 652163920

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163f661f3184663523afc2bd57e8b3f5f60557ab2f3cf45327fdb2e443f5ead9
+size 995638475

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74af94406ef982f95dc6e07cccf5a4f061ecabe8787480809f4f9cca810e949
+size 14455

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c30ad8fd786f664bc3a5a8dad4d6355bae4a8236534a42ec068df9de57c586
+size 1465

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.029858768027231197,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.9905845351487463e-05,
+      "grad_norm": 5.78125,
+      "learning_rate": 5e-05,
+      "loss": 3.0625,
+      "step": 1
+    },
+    {
+      "epoch": 0.0019905845351487466,
+      "grad_norm": 2.5,
+      "learning_rate": 4.996715568206701e-05,
+      "loss": 1.3333,
+      "step": 100
+    },
+    {
+      "epoch": 0.003981169070297493,
+      "grad_norm": 2.46875,
+      "learning_rate": 4.99339796033468e-05,
+      "loss": 1.29,
+      "step": 200
+    },
+    {
+      "epoch": 0.005971753605446239,
+      "grad_norm": 2.375,
+      "learning_rate": 4.99008035246266e-05,
+      "loss": 1.28,
+      "step": 300
+    },
+    {
+      "epoch": 0.007962338140594986,
+      "grad_norm": 2.3125,
+      "learning_rate": 4.9867627445906404e-05,
+      "loss": 1.3,
+      "step": 400
+    },
+    {
+      "epoch": 0.009952922675743733,
+      "grad_norm": 2.3125,
+      "learning_rate": 4.9834451367186206e-05,
+      "loss": 1.28,
+      "step": 500
+    },
+    {
+      "epoch": 0.011943507210892478,
+      "grad_norm": 2.25,
+      "learning_rate": 4.980127528846601e-05,
+      "loss": 1.29,
+      "step": 600
+    },
+    {
+      "epoch": 0.013934091746041224,
+      "grad_norm": 2.53125,
+      "learning_rate": 4.976809920974581e-05,
+      "loss": 1.3,
+      "step": 700
+    },
+    {
+      "epoch": 0.015924676281189973,
+      "grad_norm": 2.453125,
+      "learning_rate": 4.973492313102561e-05,
+      "loss": 1.29,
+      "step": 800
+    },
+    {
+      "epoch": 0.017915260816338718,
+      "grad_norm": 2.4375,
+      "learning_rate": 4.970174705230541e-05,
+      "loss": 1.28,
+      "step": 900
+    },
+    {
+      "epoch": 0.019905845351487466,
+      "grad_norm": 2.328125,
+      "learning_rate": 4.966857097358521e-05,
+      "loss": 1.29,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02189642988663621,
+      "grad_norm": 2.296875,
+      "learning_rate": 4.963539489486501e-05,
+      "loss": 1.28,
+      "step": 1100
+    },
+    {
+      "epoch": 0.023887014421784956,
+      "grad_norm": 2.3125,
+      "learning_rate": 4.960221881614481e-05,
+      "loss": 1.29,
+      "step": 1200
+    },
+    {
+      "epoch": 0.025877598956933704,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.956904273742461e-05,
+      "loss": 1.29,
+      "step": 1300
+    },
+    {
+      "epoch": 0.02786818349208245,
+      "grad_norm": 2.46875,
+      "learning_rate": 4.953586665870441e-05,
+      "loss": 1.28,
+      "step": 1400
+    },
+    {
+      "epoch": 0.029858768027231197,
+      "grad_norm": 2.171875,
+      "learning_rate": 4.950269057998421e-05,
+      "loss": 1.29,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 150711,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6271008768000000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e18b4325b89fb53c1fae48a92345c3dcd3152d31c361199797b2d21dc2da65cc
+size 5777